© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12799
    Prev
    Next
    INDEX
    Explanations

    the word "being" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fawcett
    -0.76
     Schott
    -0.75
     Patti
    -0.73
     NPA
    -0.73
    ctable
    -0.73
    prc
    -0.72
     Rhi
    -0.72
     flared
    -0.71
     Sart
    -0.71
     Conley
    -0.71
    POSITIVE LOGITS
     being
    2.06
     BEING
    1.87
    being
    1.81
    Being
    1.77
     Being
    1.77
     étant
    1.30
     bein
    1.18
     having
    1.05
     être
    1.02
     sendo
    0.99
    Activations Density 0.104%

    No Known Activations